Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Analyze AiM RaceStudio lap data: lap times, compare laps, time loss, compare two sessions.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://laps.mcp.rush.sr/mcpRun this in your terminal
claude mcp add --transport http lap-analyzer https://laps.mcp.rush.sr/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"lap-analyzer": {
"url": "https://laps.mcp.rush.sr/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"lap-analyzer": {
"type": "http",
"url": "https://laps.mcp.rush.sr/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://laps.mcp.rush.sr/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain rush.sr (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 36 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, SSTracker free youth training
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Free youth sports drills, practice plans and age-group answers for parents and coaches.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A remote MCP server that analyzes AiM RaceStudio lap data. It works as a connector in Claude and as a plugin in ChatGPT. Built by Rush Auto Works.
https://laps.mcp.rush.sr/mcp Streamable HTTP, no sign-in
| Tool | What it does |
|---|---|
analyze_session | Lap times, best lap, theoretical best, consistency, and which laps were excluded and why. |
compare_laps | Time delta, braking points and corner minimum speeds for two laps in one session. |
find_time_loss | The sectors where a lap loses the most time against your best lap. |
compare_sessions | Two sessions on their best valid laps: delta, sectors gained and lost, braking points, corner minimum speeds, top speed. Use it for two drivers or two cars on the same track. |
Every tool is read-only. Every result ends with one line, Built by Rush Auto Works, with a link to rushautoworks.com.
Send an AiM RaceStudio CSV export as csv_text, or attach the file where the client supports uploads. compare_sessions takes csv_text_a and csv_text_b (or file_a and file_b) and optional lap_a and lap_b. Files are limited to 8 MB, so a very long session may be rejected with a message naming the limit.
Excluded laps: the first lap (out-lap), the last segment (in-lap, because it ends with the data, not on a beacon crossing), and any lap more than 7% slower than the best.
AiM .xrk logs are binary and are not read directly. In Claude, install the Rush SR plugin, which converts an .xrk with libxrk and runs the same engine in the sandbox.
Two synthetic sessions, not from a real driver, are in examples/:
synthetic-session-a.csv: best lap 4 in 45.793 s, theoretical best 45.547 s, 4 valid laps.synthetic-session-b.csv: the same track about 3% slower. compare_sessions on the pair gives a delta of -1.416 s.It analyzes the data in memory and stores nothing. It makes no calls to a language model and needs no sign-in. A file link is downloaded once, over HTTPS, with limits on size, redirects and time. Requests pass through Amazon CloudFront and Cloudflare as infrastructure providers. Workers Logs are switched off in wrangler.jsonc, and a test fails if that changes.
Privacy policy: https://rushautoworks.com/privacy-policy/
info@rushautoworks.com, or an issue at https://github.com/Rush-Auto-Works/llm-plugins/issues.
npx wrangler deploy
ChatGPT's plugin submission checks a token at /.well-known/openai-apps-challenge on the MCP host. The dashboard issues the token when a submission draft is started. Add it to vars in wrangler.jsonc and redeploy:
"vars": { "OPENAI_APPS_CHALLENGE": "<token from the ChatGPT plugins dashboard>" }
The route returns the token as plain text. Until the variable is set it returns 404, so nothing is served by default. Check it with curl https://laps.mcp.rush.sr/.well-known/openai-apps-challenge.
npm ci
npm test # boots wrangler dev and runs the E2E suite npm run dev # http://127.0.0.1:8787/mcp
MIT licensed.